{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3RPA26XDFVF4OXYWE7KFA3ZR2M","short_pith_number":"pith:3RPA26XD","schema_version":"1.0","canonical_sha256":"dc5e0d7ae32d4bc75f1627d4506f31d3228b60192905eefbf53b8ff1de26492b","source":{"kind":"arxiv","id":"2410.16069","version":2},"attestation_state":"computed","paper":{"title":"Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aline Villavicencio, Maggie Mi, Nafise Sadat Moosavi","submitted_at":"2024-10-21T14:47:37Z","abstract_excerpt":"Human processing of idioms relies on understanding the contextual sentences in which idioms occur, as well as language-intrinsic features such as frequency and speaker-intrinsic factors like familiarity. While LLMs have shown high performance on idiomaticity detection tasks, this success may be attributed to reasoning shortcuts in existing datasets. To this end, we construct a novel, controlled contrastive dataset designed to test whether LLMs can effectively use context to disambiguate idiomatic meaning. Additionally, we explore how collocational frequency and sentence probability influence m"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.16069","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T14:47:37Z","cross_cats_sorted":[],"title_canon_sha256":"dd2efb6f47d3f8a7fbc3db97c123a1fd2adcb2d42c7c15dc3d8c2af8b31d4d6f","abstract_canon_sha256":"6a3454e16dea05c046c00dc09611d0d96d84bcee593d4ac89bf1280e28cc2517"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:42.818859Z","signature_b64":"5Asgde/bRS4qNUYE982yv0YQHD8PZbijYxvJsHpKvEA0ZoV4eSAa1UH/IcU7pXIzO7CXkcESsPaziATkgE0lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc5e0d7ae32d4bc75f1627d4506f31d3228b60192905eefbf53b8ff1de26492b","last_reissued_at":"2026-07-05T11:37:42.818204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:42.818204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aline Villavicencio, Maggie Mi, Nafise Sadat Moosavi","submitted_at":"2024-10-21T14:47:37Z","abstract_excerpt":"Human processing of idioms relies on understanding the contextual sentences in which idioms occur, as well as language-intrinsic features such as frequency and speaker-intrinsic factors like familiarity. While LLMs have shown high performance on idiomaticity detection tasks, this success may be attributed to reasoning shortcuts in existing datasets. To this end, we construct a novel, controlled contrastive dataset designed to test whether LLMs can effectively use context to disambiguate idiomatic meaning. Additionally, we explore how collocational frequency and sentence probability influence m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16069","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.16069/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.16069","created_at":"2026-07-05T11:37:42.818285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16069v2","created_at":"2026-07-05T11:37:42.818285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16069","created_at":"2026-07-05T11:37:42.818285+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RPA26XDFVF4","created_at":"2026-07-05T11:37:42.818285+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RPA26XDFVF4OXYW","created_at":"2026-07-05T11:37:42.818285+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RPA26XD","created_at":"2026-07-05T11:37:42.818285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M","json":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M.json","graph_json":"https://pith.science/api/pith-number/3RPA26XDFVF4OXYWE7KFA3ZR2M/graph.json","events_json":"https://pith.science/api/pith-number/3RPA26XDFVF4OXYWE7KFA3ZR2M/events.json","paper":"https://pith.science/paper/3RPA26XD"},"agent_actions":{"view_html":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M","download_json":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M.json","view_paper":"https://pith.science/paper/3RPA26XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16069&json=true","fetch_graph":"https://pith.science/api/pith-number/3RPA26XDFVF4OXYWE7KFA3ZR2M/graph.json","fetch_events":"https://pith.science/api/pith-number/3RPA26XDFVF4OXYWE7KFA3ZR2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M/action/storage_attestation","attest_author":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M/action/author_attestation","sign_citation":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M/action/citation_signature","submit_replication":"https://pith.science/pith/3RPA26XDFVF4OXYWE7KFA3ZR2M/action/replication_record"}},"created_at":"2026-07-05T11:37:42.818285+00:00","updated_at":"2026-07-05T11:37:42.818285+00:00"}